CN111703366A - Attention reminder device for vehicle, attention reminder method for vehicle, and recording medium - Google Patents

Abstract

Translated fromChinese

本发明提供车辆用注意提醒装置、车辆用注意提醒方法及记录介质。所述车辆用注意提醒装置(2000)在乘员进行包含与驾驶相关的注意信息的会话的情况下，进行注意提醒。该车辆用注意提醒装置(2000)具备：语音输入部(300)，其输入车辆(1000)的乘员(10、12、14、16、18、20)的声音；话语推断部(400)，其基于语音来推断话语；注意信息判定部(500)，其判定话语中是否包含与车辆的驾驶相关的注意信息；以及输出部(800)，其在话语中包含注意信息的情况下输出通知信息。

The present invention provides an attention reminding device for vehicles, an attention reminding method for vehicles, and a recording medium. The vehicle caution reminder device (2000) issues a caution reminder when an occupant has a conversation including caution information related to driving. The vehicle attention warning device (2000) includes: a voice input unit (300) for inputting voices of occupants (10, 12, 14, 16, 18, 20) of the vehicle (1000); and a speech inference unit (400) for An utterance is inferred based on the speech; an attention information determination section (500) that determines whether the utterance contains attention information related to driving of the vehicle; and an output section (800) that outputs notification information if the utterance contains attention information.

Description

Translated fromChinese

车辆用注意提醒装置、车辆用注意提醒方法及记录介质Attention reminder device for vehicle, attention reminder method for vehicle, and recording medium

技术领域technical field

本发明涉及车辆用注意提醒装置、车辆用注意提醒方法及记录介质。The present invention relates to a vehicle attention reminder device, a vehicle attention reminder method and a recording medium.

背景技术Background technique

以往，在例如下述的专利文献1中记载了车载信息装置，其搭载于车辆，提供辅助搭乘者的信息，该车载信息装置具备：声音获取部，检测并获取搭乘者所发出的声音；语音识别部，识别由声音获取部获取到的上述声音的话语内容；输出控制部，将由语音识别部识别到的上述话语内容作为显示数据或声音数据进行生成和输出控制；以及输出部，输出由输出控制部生成的显示数据或声音数据。Conventionally, for example, Patent Document 1 described below describes an in-vehicle information device that is mounted on a vehicle and provides information to assist passengers, the in-vehicle information device includes: a sound acquisition unit that detects and acquires the sound uttered by the passenger; a recognition unit for recognizing the speech content of the voice acquired by the voice acquisition unit; an output control unit for generating and outputting the speech content recognized by the speech recognition unit as display data or voice data; and an output unit for outputting Display data or sound data generated by the control unit.

现有技术文献prior art literature

专利文献Patent Literature

专利文献1：国际公开第2014/002128号Patent Document 1: International Publication No. 2014/002128

发明内容SUMMARY OF THE INVENTION

技术问题technical problem

在车辆的驾驶中，乘员有时进行包含与驾驶有关的注意信息的会话。在该情况下，如果注意信息预先传递给车辆的驾驶员(驾驶者)，则使驾驶员能够专注驾驶，便利性高。但是，在上述专利文献1所记载的技术中，虽然假定识别到搭乘者所发出的话语内容，并作为显示数据或声音数据而输出，但是针对话语内容中包含与驾驶相关的注意信息的处理方法，没有任何考虑。During the driving of the vehicle, the occupant sometimes has a conversation including caution information related to driving. In this case, if the attention information is transmitted to the driver (driver) of the vehicle in advance, the driver can concentrate on driving, and the convenience is high. However, in the technique described in the above-mentioned Patent Document 1, it is assumed that the content of the utterance uttered by the passenger is recognized and output as display data or voice data, but the method of processing the content of the utterance includes caution information related to driving , without any consideration.

因此，本发明是鉴于上述问题而完成的，本发明的目的在于，提供在乘员进行包含与驾驶相关的注意信息的会话的情况下，能够进行注意提醒的新型且经过改良的车辆用注意提醒装置、车辆用注意提醒方法及记录介质。Therefore, the present invention has been made in view of the above-mentioned problems, and an object of the present invention is to provide a new and improved vehicle caution reminder device capable of performing a caution reminder when an occupant conducts a conversation including caution information related to driving , Vehicle use caution reminder method and recording medium.

技术方案Technical solutions

为了解决上述课题，根据本发明的一个观点，提供车辆用注意提醒装置，其具备：语音输入部，其输入车辆的乘员的声音；话语推断部，其基于上述声音来推断话语；注意信息判定部，其判定在上述话语中是否包含与上述车辆的驾驶相关的注意信息；以及通知部，其在上述话语中包含上述注意信息的情况下进行通知。In order to solve the above-mentioned problems, according to an aspect of the present invention, there is provided an attention warning device for a vehicle, comprising: a speech input unit for inputting a voice of a vehicle occupant; a speech inference unit for inferring speech based on the speech; an attention information determination unit , which determines whether or not caution information related to driving of the vehicle is included in the utterance; and a notification unit that notifies when the utterance contains the caution information.

在上述话语中包含上述注意信息的情况下，上述输出部可以输出上述话语。When the above-mentioned utterance includes the above-mentioned attention information, the above-mentioned output unit may output the above-mentioned utterance.

在上述话语中包含上述注意信息的情况下，上述输出部可以强调并输出上述话语。另外，上述输出部不仅可以向车厢内输出或发送信息，还可以向车厢外输出或发送信息。In the case where the above-mentioned attention information is included in the above-mentioned utterance, the above-mentioned output unit may emphasize and output the above-mentioned utterance. In addition, the above-mentioned output unit may output or transmit information not only to the inside of the vehicle but also to the outside of the vehicle.

另外，上述车辆用注意提醒装置可以具备将推断出的上述话语转换成文字信息的文字转换部，上述通知部包含将上述文字信息转换成语音的语音转换部，并将上述通知输出到扬声器。另外，上述转换部可以进行翻译、摘要等。Further, the vehicle attention warning device may include a character conversion unit that converts the estimated speech into character information, the notification unit includes a voice conversion unit that converts the character information into speech, and outputs the notification to a speaker. In addition, the above-mentioned conversion unit may perform translation, abstract, and the like.

另外，上述通知部可以包含在上述话语中包含上述注意信息的情况下，强调经过上述转换的语音的音量的语音强调部。In addition, the notification unit may include a speech emphasis unit that emphasizes the volume of the converted speech when the attention information is included in the speech.

另外，上述车辆用注意提醒装置可以具备将推断出的上述话语转换成文字信息的文字转换部，上述通知部将上述通知输出到显示装置。Further, the vehicle attention warning device may include a character conversion unit that converts the estimated speech into character information, and the notification unit may output the notification to the display device.

另外，上述通知部可以包含在上述话语中包含上述注意信息的情况下，强调上述文字信息的文字强调部。Further, the notification unit may include a character emphasis unit for emphasizing the character information when the caution information is included in the utterance.

另外，所述车辆用注意提醒装置可以具备确定作为上述注意信息的输出目标的被信息提示者的被信息提示者确定部，上述被信息提示者确定部在上述话语中包含上述注意信息的情况下，将上述车辆的驾驶员确定为上述被信息提示者。Further, the vehicular attention reminder device may include an information-presented person specifying unit for specifying an information-presented person who is an output destination of the caution information, and the information-presented person specifying unit may include the caution information in the utterance. , and the driver of the vehicle is determined as the person to be presented with the information.

另外，上述在上述话语中包含上述注意信息的情况下，被信息提示者确定部可以将上述车辆的乘员全员确定为上述被信息提示者。In addition, when the above-mentioned attention information is included in the above-mentioned utterance, the information-presented person specifying unit may specify all the occupants of the vehicle as the information-presented person.

另外，为了解决上述课题，根据本发明的另一观点，提供车辆用注意提醒方法，其包括：输入车辆的乘员的语音的步骤；基于上述语音来推断话语的步骤；判定上述话语中是否包含与上述车辆的驾驶相关的注意信息的步骤；以及在上述话语中包含上述注意信息的情况下进行通知的步骤。In addition, in order to solve the above-mentioned problems, according to another aspect of the present invention, there is provided a vehicle attention warning method comprising: the steps of inputting the voice of the occupant of the vehicle; the step of estimating the utterance based on the voice; the step of notifying the above-mentioned caution information related to the driving of the vehicle; and the step of notifying when the above-mentioned utterance contains the above-mentioned caution information.

另外，为了解决上述课题，根据本发明的另一观点，提供记录介质，用于使计算机作为如下装置而发挥功能：输入车辆的乘员的语音的装置；基于上述语音来推断话语的装置；判定上述话语中是否包含与上述车辆的驾驶相关的注意信息的装置；以及在上述话语中包含上述注意信息的情况下进行通知的装置。In order to solve the above-mentioned problems, according to another aspect of the present invention, there is provided a recording medium for causing a computer to function as a device for inputting the voice of an occupant of a vehicle; a device for estimating speech based on the voice; A device for whether or not the utterance contains caution information related to driving of the vehicle; and a device for notifying when the utterance contains the caution information.

发明效果Invention effect

根据本发明，在乘员进行包含与驾驶相关的注意信息的会话的情况下，能够进行提醒注意。According to the present invention, when the occupant has a conversation including caution information related to driving, it is possible to call attention.

附图说明Description of drawings

图1是表示本发明的一个实施方式的车辆的平面构成的示意图。FIG. 1 is a schematic diagram showing a plane configuration of a vehicle according to an embodiment of the present invention.

图2是表示本实施方式的车辆用注意提醒装置的构成的示意图。FIG. 2 is a schematic diagram showing the configuration of the vehicle caution warning device according to the present embodiment.

图3是表示通过本实施方式的车辆用注意提醒装置进行的处理的流程图。FIG. 3 is a flowchart showing a process performed by the vehicle attention warning device of the present embodiment.

符号说明Symbol Description

10、12、14、16、18、20：乘员10, 12, 14, 16, 18, 20: Crew

200、202、204、206、208、210：扬声器200, 202, 204, 206, 208, 210: Speakers

250、252、254、256、258、260：显示器(显示装置)250, 252, 254, 256, 258, 260: Displays (display devices)

300：语音输入部300: Voice input section

400：话语推断部400: Discourse Inference Department

450：文本转换部450: Text Conversion Department

500：注意信息判断部500: Attention Information Judgment Department

600：被信息提示者确定部600: Determination of the person to be informed by the information

700：语音合成部700: Speech Synthesis Department

710：文字/语音转换部710: Text/Voice Conversion Department

720：语音强调部720: Voice Emphasis Department

800：输出部800: Output section

900：文字合成部900: Text Synthesis Department

910：文字强调部910: Text Emphasis

1000：车辆1000: Vehicle

2000：车辆用注意提醒装置2000: Attention reminder devices for vehicles

具体实施方式Detailed ways

以下，参照附图，对本发明的优选实施方式进行详细说明。应予说明，在本说明书和附图中，通过对实质上具有相同功能构成的构成要素标注相同符号，从而省略重复的说明。Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In addition, in this specification and drawings, the same code|symbol is attached|subjected to the component which has substantially the same functional structure, and the repeated description is abbreviate|omitted.

图1是表示本发明的一个实施方式的车辆1000的平面构成的示意图。如图1所示，在车辆中有6名乘员10、12、14、16、18、20。6名中的乘员10为车辆的驾驶员。FIG. 1 is a schematic diagram showing a plan configuration of avehicle 1000 according to an embodiment of the present invention. As shown in FIG. 1 , there are sixoccupants 10 , 12 , 14 , 16 , 18 , and 20 in the vehicle. Theoccupant 10 among the six is the driver of the vehicle.

在车辆1000内设置有多个扬声器200、202、204、206、208、210。扬声器200朝向作为驾驶员的乘员10发出声音。同样地，扬声器202、204、206、208、210分别与相近的乘员12、14、16、18、20相对应地设置，朝向乘员12、14、16、18、20发出声音。A plurality ofspeakers 200 , 202 , 204 , 206 , 208 , and 210 are provided in thevehicle 1000 . Thespeaker 200 emits sound toward theoccupant 10 as the driver. Likewise,speakers 202 , 204 , 206 , 208 , 210 are positioned corresponding toadjacent occupants 12 , 14 , 16 , 18 , 20 , respectively, and emit sounds towardoccupants 12 , 14 , 16 , 18 , 20 .

另外，在车辆1000内设置有多个显示器(显示装置)250、252、254、256、258、260。显示器250朝向作为驾驶员的乘员10进行显示。同样地，显示器252、254、256、258、260分别与相近的乘员12、14、16、18、20相对应地设置，朝向乘员12、14、16、18、20进行显示。In addition, a plurality of displays (display devices) 250 , 252 , 254 , 256 , 258 , and 260 are provided in thevehicle 1000 . Thedisplay 250 is displayed toward theoccupant 10 as the driver. Likewise, thedisplays 252 , 254 , 256 , 258 , and 260 are provided corresponding to theadjacent occupants 12 , 14 , 16 , 18 , and 20 , respectively, and display toward theoccupants 12 , 14 , 16 , 18 , and 20 .

另外，在车辆1000内设置有3个麦克风100、102、104。麦克风100收集前排的乘员10和乘员12的声音。麦克风102收集中排的乘员14和乘员16的声音。另外，麦克风104收集后排的乘员18和乘员20的声音。In addition, threemicrophones 100 , 102 , and 104 are provided in thevehicle 1000 . Themicrophone 100 collects the voices of theoccupants 10 and 12 in the front row. Themicrophone 102 collects the voices of theoccupants 14 and 16 in the middle row. Additionally, themicrophones 104 collect the voices of theoccupants 18 and 20 in the rear.

然而，在车辆1000内，有时因为声音而阻碍会话。例如，在车内聆听音乐的情况、在打开车窗的情况下等，有时因会话以外的声音而阻碍会话。However, in thevehicle 1000, the conversation is sometimes hindered by the sound. For example, when listening to music in a car, when opening a car window, etc., the conversation may be hindered by sounds other than the conversation.

在本实施方式中，利用麦克风100、102、104收集乘员10、12、14、16、18、20的声音，并将其从扬声器200、202、204、206、208、210输出。特别是，在本实施方式中，对于由麦克风100、102、104收集到的声音，在暂时将语音转换为文本信息(文字信息)之后，再从文本信息再次转换成语音，从扬声器200、202、204、206、208、210输出。另外，在将由麦克风100、102、104收集到的声音转换成文本信息之后，将其显示于显示器250、252、254、256、258、260。由此，能够抑制对会话造成阻碍。应予说明，在从扬声器200、202、204、206、208、210输出语音的情况下，可以不进行文本转换。In the present embodiment, the sounds of thepassengers 10 , 12 , 14 , 16 , 18 , and 20 are collected by themicrophones 100 , 102 , and 104 , and output from thespeakers 200 , 202 , 204 , 206 , 208 , and 210 . In particular, in the present embodiment, the voices collected by themicrophones 100 , 102 , and 104 are temporarily converted into text information (text information), and then the text information is converted into voice again. , 204, 206, 208, 210 output. In addition, after the voices collected by themicrophones 100 , 102 , and 104 are converted into text information, they are displayed on thedisplays 250 , 252 , 254 , 256 , 258 , and 260 . Thereby, it is possible to suppress blocking of the conversation. In addition, in the case of outputting a voice from thespeakers 200 , 202 , 204 , 206 , 208 , and 210 , the text conversion need not be performed.

另外，在乘员的会话中，在包含与车辆的驾驶相关的注意信息。例如，在乘员彼此进行“有车辆从右侧接近！”、“前方逼近堵车的末尾”、“与前车之间的车间距离变短”、“前方的道路冻结”等会话时，这些会话包含注意信息。因此，在本实施方式中，判定会话中是否包含注意信息，在包含注意信息的情况下，强调该话语并从扬声器200、202、204、206、208、210输出。特别是，在本实施方式中，在会话中包含注意信息的情况下，从扬声器200向作为驾驶员的乘员10强调并输出话语。由此，驾驶员能够注意到成为注意信息的根源的现象，并能够进行适当的处理。In addition, attention information related to driving of the vehicle is included in the conversation of the occupant. For example, when the occupants have conversations with each other such as "There is a vehicle approaching from the right!", "The end of the traffic jam is approaching ahead", "The inter-vehicle distance to the vehicle in front is shortened", "The road ahead is frozen", etc., these conversations contain Attention information. Therefore, in the present embodiment, it is determined whether or not attention information is included in the conversation, and if the attention information is included, the speech is emphasized and output from thespeakers 200 , 202 , 204 , 206 , 208 , and 210 . In particular, in the present embodiment, when attention information is included in the conversation, thespeaker 200 emphasizes and outputs the utterance to theoccupant 10 as the driver. As a result, the driver can notice the phenomenon that is the source of the attention information, and can take appropriate measures.

例如，在会话中包含“有车辆从右侧接近！”这一注意信息的情况下，通过将该话语从作为驾驶员的乘员10的扬声器200输出，从而能够使驾驶员进行左打方向盘等适当的处理，能够避免与接近的车辆的接触。另外，在会话中包含“前方的道路冻结”这一注意信息的情况下，能够使驾驶员进行预先踩下制动器而降低速度等适当的处理，能够避免打滑。For example, when the conversation contains the caution information "A vehicle is approaching from the right side!", by outputting the utterance from thespeaker 200 of theoccupant 10 as the driver, the driver can appropriately turn the steering wheel to the left or the like. processing to avoid contact with approaching vehicles. In addition, when the caution information "the road ahead is frozen" is included in the conversation, the driver can be made to perform appropriate processing such as depressing the brake in advance to reduce the speed, thereby avoiding slippage.

图2是表示本实施方式的车辆用注意提醒装置2000的构成的示意图。如图2所示，车辆用注意提醒装置2000除了构成为具有麦克风100、102、104、扬声器200、202、204、206、208、210、显示器250、252、254、256、258、260以外，还具有语音输入部300、话语推断部400、注意信息判定部500、被信息提示者确定部600、输出部800。输出部800具有语音合成部700，语音合成部700包含文字/语音转换部710、语音强调部720。另外，输出部800具有文字合成部900，文字合成部900包含文字强调部910。应予说明，图2所示的车辆用注意提醒装置2000的各构成要素可以由电路(硬件)或CPU等中央运算处理装置以及用于使其发挥功能的程序(软件)构成。FIG. 2 is a schematic diagram showing the configuration of a vehiclecaution warning device 2000 according to the present embodiment. As shown in FIG. 2 , in addition to havingmicrophones 100 , 102 , 104 ,speakers 200 , 202 , 204 , 206 , 208 , and 210 , and displays 250 , 252 , 254 , 256 , 258 , and 260 , the vehicleattention warning device 2000 has a configuration. It also includes aspeech input unit 300 , anutterance inference unit 400 , an attentioninformation determination unit 500 , an information-presentedperson identification unit 600 , and anoutput unit 800 . Theoutput unit 800 includes aspeech synthesis unit 700 , and thespeech synthesis unit 700 includes a character/speech conversion unit 710 and aspeech emphasis unit 720 . In addition, theoutput unit 800 includes acharacter synthesis unit 900 , and thecharacter synthesis unit 900 includes acharacter emphasis unit 910 . In addition, each component of thecaution warning apparatus 2000 for vehicles shown in FIG. 2 can be comprised by the central processing unit, such as a circuit (hardware), CPU, and a program (software) for making it function.

向语音输入部300输入由麦克风100、102、104收集到的乘员10、12、14、16、18、20的语音。所输入的语音被发送到话语推断部400。在话语推断部400中，进行语音识别，推断乘员彼此的会话所含的话语。应予说明，话语推断部400不仅能够推断话语，还能够推断话语(话语的内容)。作为话语的例子，例如可举出乘员所发出的“人！”、“石！”等。The voices of theoccupants 10 , 12 , 14 , 16 , 18 , and 20 collected by themicrophones 100 , 102 , and 104 are input to thevoice input unit 300 . The input speech is sent to thespeech inference unit 400 . In thespeech inference unit 400, speech recognition is performed, and speech included in the conversation between the occupants is estimated. It should be noted that thespeech inference unit 400 can infer not only speech but also speech (content of speech). As an example of the speech, for example, "people!"

具体而言，在话语推断部400中，将处理大致分成2种功能，进行声音分析和语音识别。在声音分析中进行声音的符号化、噪音处理、校正等。在语音识别中，通过声音处理、语言处理对声音分析而得的符号化语音数据进行语音识别，提取概率最高的单词或字符串。因此，话语推断部400包含将语音数据转换成文本信息的文字转换部450。该声音分析、语音识别使用声音模型、语言模型。另外，注册了各模型所利用的生硬图案、单词或字符串等的是词典，可以通过丰富词典来提高识别率。应予说明，由话语推断部400进行的话语的推断例如可以适当使用上述专利文献1所记载的方法、日本特开2003-323191号公报等记载的方法等。Specifically, in thespeech inference unit 400, processing is roughly divided into two functions, and speech analysis and speech recognition are performed. In the sound analysis, the symbolization of sound, noise processing, correction, etc. are performed. In speech recognition, speech recognition is performed on the symbolic speech data obtained by sound analysis through sound processing and language processing, and words or character strings with the highest probability are extracted. Therefore, thespeech inference unit 400 includes acharacter conversion unit 450 that converts the speech data into text information. The voice analysis and voice recognition use a voice model and a language model. In addition, a dictionary is used to register hard patterns, words, character strings, etc. used by each model, and the recognition rate can be improved by enriching the dictionary. It should be noted that, for the estimation of the utterance by theutterance inference unit 400, for example, the method described in the above-mentioned Patent Document 1, the method described in Japanese Patent Laid-Open No. 2003-323191, and the like can be appropriately used.

如果通过话语推断部400识别到语音数据，并转换成文本信息，则将文本信息发送到输出部(通知部)800的语音合成部700、文字合成部900。另外，还将文本信息发送到注意信息判定部500。在注意信息判定部500中，判断文本信息中是否包含注意信息。例如，注意信息判定部500通过进行关键词检测来判断文本信息中是否包含注意信息。作为关键词，例如可举出“堵车”、“雨”、“雪”、“后方车辆”、“相邻车道”、“路面”、“汽油”等。注意信息判定部500包含存储有这些关键词的数据库。在文本信息中包含这些关键词的情况下，注意信息判定部500判断为文本信息中包含注意信息。在文本信息中包含注意信息的情况下，将该情况发送到语音合成部700的语音强调部720、文字合成部800的文字强调部810。When the speech data is recognized by thespeech inference unit 400 and converted into text information, the text information is sent to thespeech synthesis unit 700 and thecharacter synthesis unit 900 of the output unit (notification unit) 800 . In addition, text information is also sent to the attentioninformation determination unit 500 . The cautioninformation determination unit 500 determines whether or not caution information is included in the text information. For example, the cautioninformation determination unit 500 determines whether or not caution information is included in the text information by performing keyword detection. As a keyword, "traffic jam", "rain", "snow", "rear vehicle", "adjacent lane", "road surface", "gasoline" etc. are mentioned, for example. The attentioninformation determination unit 500 includes a database in which these keywords are stored. When these keywords are included in the text information, the cautioninformation determination unit 500 determines that the text information includes caution information. When the text information includes caution information, the information is sent to thespeech emphasis unit 720 of thespeech synthesis unit 700 and the character emphasis unit 810 of thecharacter synthesis unit 800 .

在文本信息中包含注意信息的情况下，输出部800输出用于向乘员通知注意信息的通知信息。因此，输出部800的语音合成部700包含语音强调部720，文字合成部900包含文字强调部910。输出部800可以发出用于唤起注意的声音、光。When the text information includes caution information, theoutput unit 800 outputs notification information for notifying the occupant of the caution information. Therefore, thespeech synthesis unit 700 of theoutput unit 800 includes thespeech emphasis unit 720 , and thecharacter synthesis unit 900 includes thecharacter emphasis unit 910 . Theoutput unit 800 can emit sound and light for calling attention.

如果向语音合成部700输入通过话语推断部400的推断得到的文本信息，则文字/语音转换部710进行将文本信息转换成语音的处理。具体而言，文字/语音转换部710进行从字符串合成语音的处理。作为从字符串合成语音的方法，例如可以适当使用日本专利第5512597号公报中记载的方法等。语音合成是通过保持有将字符串、单词与音素符号的集合相关联的数据库(DB)以及将各音素符号与波形相关联的数据库(DB)，将文字信息转换成音素符号的序列，并将其转换成波形而实现的。When text information obtained by the inference of thespeech inference unit 400 is input to thespeech synthesis unit 700, the character/speech conversion unit 710 performs a process of converting the text information into speech. Specifically, the character/speech conversion unit 710 performs a process of synthesizing speech from a character string. As a method of synthesizing speech from character strings, for example, a method described in Japanese Patent No. 5512597 or the like can be appropriately used. Speech synthesis is to convert text information into a sequence of phoneme symbols by maintaining a database (DB) that associates strings, words, and sets of phoneme symbols, and a database (DB) that associates each phoneme symbol with waveforms, and converts text information into a sequence of phoneme symbols. It is realized by converting it into a waveform.

在文本信息中包含注意信息的情况下，语音强调部720使通过文字/语音转换部710进行的转换而得到的语音的音量变化。更具体而言，在文本信息中包含注意信息的情况下，语音强调部720使通过文字/语音转换部710进行的转换而得到的语音的音量增大。另外，语音强调部720也可以采用使音量增大的方法以外的方法来强调语音。语音强调部720可以通过使音质变化、多次重复注意信息、使话语速度变化等方法来强调语音。例如，通过使与1个音信号对应地变化的电压的频率变化，能够使话语速度变化。在增大音量的情况下，语音强调部720通过改变向扬声器200、202、204、206、208、210的电压给予的一律的系数而使音量变化。利用语音强调部720使音量变化之后，从扬声器200、202、204、206、208、210输出语音。应予说明，在语音合成部700中，基本上在从扬声器输出乘员的会话时强调并输出会话的语音，但是也可以为了进行注意提醒而输出警报音，或输出固定格式的语音等。When the attention information is included in the text information, thespeech emphasis unit 720 changes the volume of the speech obtained by the conversion by the character/speech conversion unit 710 . More specifically, when the text information includes attention information, thevoice emphasis unit 720 increases the volume of the voice converted by the character/voice conversion unit 710 . In addition, thespeech emphasis unit 720 may emphasize speech by a method other than the method of increasing the volume. Thespeech emphasis unit 720 can emphasize speech by changing the sound quality, repeating the attention information multiple times, changing the speech speed, and the like. For example, the speech speed can be changed by changing the frequency of the voltage that changes according to one sound signal. When the volume is increased, thespeech emphasis unit 720 changes the volume by changing the uniform coefficients given to the voltages of thespeakers 200 , 202 , 204 , 206 , 208 , and 210 . After the volume is changed by thevoice emphasis unit 720 , voices are output from thespeakers 200 , 202 , 204 , 206 , 208 , and 210 . Thespeech synthesis unit 700 basically emphasizes and outputs the speech of the conversation when the occupant's conversation is output from the speaker, but may output an alarm sound or output a fixed-format speech or the like for warning attention.

如果向文字合成部900输入通过话语推断部400的推断而得到的文本信息，则文字强调部910在文本信息中包含注意信息的情况下，进行强调注意信息的处理。更具体而言，文字强调部910通过进行使与注意信息相应的字符串变粗、改变颜色、增大字体大小、进行闪烁等处理来强调。利用文字强调部910强调注意信息之后，在显示器250、252、254、256、258、260显示话语内容。When text information obtained by the inference of theutterance inference unit 400 is input to thecharacter synthesis unit 900, thecharacter emphasis unit 910 performs processing for emphasizing the attention information when the text information includes attention information. More specifically, thecharacter emphasis unit 910 performs processing such as making the character string corresponding to the attention information thicker, changing the color, increasing the font size, and performing blinking and the like. After the attention information is emphasized by thecharacter emphasis unit 910 , the content of the utterance is displayed on thedisplays 250 , 252 , 254 , 256 , 258 , and 260 .

被信息提示者确定部600确定成为提示信息的对象的乘员。在文本信息包含注意信息的情况下，被信息提示者确定部600将作为驾驶员的乘员10确定为被信息提示者。另一方面，在文本信息不包含注意信息的情况下，被信息提示者确定部600将所有的乘员10、12、14、16、18、20确定为被信息提示者。这样，以仅向通过被信息提示者确定部600确定的被信息提示者提示有关语音的信息的方式确定输出目标的扬声器。The occupant to whom the information is presented is identified by the informationpresenter identifying unit 600 . When the text information includes caution information, the information-presentedperson specifying unit 600 specifies theoccupant 10 as the driver as the information-presented person. On the other hand, when the text information does not include caution information, the information-presentedperson specifying unit 600 specifies all theoccupants 10 , 12 , 14 , 16 , 18 , and 20 as the information-presented persons. In this way, the speaker of the output destination is determined so as to present only the information-presented person identified by the information-presentedperson specifying unit 600 with the information about the voice.

应予说明，即使在文本信息包含注意信息的情况下，也可以将作为驾驶员的乘员10和副驾驶席的乘员12确定为被信息提示者等向多个乘员进行信息提示。Note that even when the text information includes caution information, theoccupant 10 serving as the driver and theoccupant 12 in the passenger seat may be identified as persons to be presented with information, and the like may be used to present information to a plurality of occupants.

应予说明，可以根据进行文本转换之前的语音数据判定是否包含注意信息，基于判定结果，进行上述语音的强调处理、文字的强调处理。It should be noted that it is possible to determine whether or not the attention information is included from the speech data before the text conversion is performed, and based on the determination result, the above-mentioned speech emphasis processing and character emphasis processing may be performed.

语音数据中是否包含注意信息的9的判定可以通过比较语音信息的时间序列的频率解析结果与注意信息的关键词的频率特性来进行。The determination of 9 whether or not the attention information is included in the speech data can be performed by comparing the frequency analysis result of the time series of the speech information with the frequency characteristics of the keywords of the attention information.

接下来，基于图3的流程图，对由本实施方式的车辆用注意提醒装置2000进行的处理进行说明。应予说明，在图3中，以通过语音合成部700进行的处理为例对输出部800的处理进行说明，但是由文字合成部900进行的处理也同样地进行。首先，在步骤S10中，判定是否向语音输入部300输入语音，在向语音输入部300输入了语音的情况下进入步骤S12。在步骤S12中，话语推断部400进行话语的推断，进行话语的文本化。在后续步骤S14中，注意信息判定部500判定在文本化的话语中是否包含注意信息，在话语中包含注意信息的情况下进入步骤S16。Next, based on the flowchart of FIG. 3 , the processing performed by the vehicleattention warning device 2000 of the present embodiment will be described. In addition, in FIG. 3, although the process performed by thespeech synthesis unit 700 is used as an example, the process of theoutput part 800 is demonstrated, but the process performed by thecharacter synthesis part 900 is performed similarly. First, in step S10, it is determined whether or not a voice is input to thevoice input unit 300, and when the voice is input to thevoice input unit 300, the process proceeds to step S12. In step S12, theutterance inference unit 400 performs utterance inference and textualization of the utterance. In subsequent step S14, the attentioninformation determination unit 500 determines whether or not attention information is included in the textualized utterance, and when the utterance includes attention information, the process proceeds to step S16.

在步骤S16中，被信息提示者确定部600仅将驾驶员确定为被提示信息者(乘员10)。在后续步骤S18中，语音合成部700的文字/语音转换部710将文本化的话语转换为语音。In step S16, the information-presentedperson specifying unit 600 specifies only the driver as the information-presented person (occupant 10). In the subsequent step S18, the text/voice conversion unit 710 of thespeech synthesis unit 700 converts the textualized utterance into speech.

在后续步骤S20中，语音强调部720将通过文字/语音转换部10进行的转换而得到的语音的音量提高。在后续步骤S22中，从作为驾驶员的乘员10附近的扬声器200输出语音。在步骤S22之后结束处理。In the subsequent step S20 , thevoice emphasis unit 720 increases the volume of the voice obtained by the conversion by the character/voice conversion unit 10 . In the subsequent step S22, a voice is output from thespeaker 200 near theoccupant 10 as the driver. The process ends after step S22.

另一方面，在步骤S14中，在文本化的话语中不包含注意信息的情况下，进入步骤S24。在步骤S24中，被信息提示者确定部600将所有的乘员10、12、14、16、18、20确定为被提示信息者。在后续步骤S26中，语音合成部700的文字/语音转换部710将文本化的话语转换为语音。On the other hand, in step S14, when the attention information is not included in the textualized utterance, the process proceeds to step S24. In step S24 , the information-presentedperson specifying unit 600 specifies all theoccupants 10 , 12 , 14 , 16 , 18 , and 20 as information-presented persons. In the subsequent step S26, the text/voice conversion unit 710 of thespeech synthesis unit 700 converts the textualized utterance into speech.

在步骤S26之后进入步骤S22。此时，由于在话语中不包含注意信息，所以不通过语音强调部720进行音量的改变，从所有的扬声器200、202、204、206、208、210输出语音。在步骤S22之后结束处理。After step S26, it progresses to step S22. At this time, since attention information is not included in the utterance, the voice is output from all thespeakers 200 , 202 , 204 , 206 , 208 , and 210 without changing the volume by thevoice emphasis unit 720 . The process ends after step S22.

应予说明，在图3的处理中，在步骤S14中，在文本化的话语中不包含注意信息的情况下，从扬声器向所有的乘员输出了语音，但是在文本化的话语中不包含注意信息的情况下，也可以不从扬声器输出声音。此时，不进行扬声器的扩声，而是进行通常的会话。In addition, in the process of FIG. 3 , in step S14, when the textual utterance does not include caution information, voice is output from the speaker to all the occupants, but the textual utterance does not include caution. In the case of information, it is not necessary to output sound from the speaker. At this time, the sound reinforcement by the speaker is not performed, but a normal conversation is performed.

在本实施方式中，在乘员的会话内容中包含与驾驶相关的注意信息的情况下，对提醒驾驶者注意的情况进行了说明，但是也可以将注意信息用于车辆控制。例如，在会话中包含“车辆从右侧接近！”这一注意信息的情况下，可以以使车辆向左转向的方式进行控制。In the present embodiment, the case where the driver's attention is called when the driver's conversation content includes the driver's attention information has been described, but the attention information may be used for vehicle control. For example, when the conversation contains the attention information "The vehicle is approaching from the right side!", the control may be performed so that the vehicle is turned to the left.

如上所述，根据本实施方式，在乘员的会话内容中包含与驾驶相关的注意信息的情况下，可以对驾驶者提醒注意。因此，能够基于注意信息最佳地驾驶车辆。As described above, according to the present embodiment, when caution information related to driving is included in the conversation content of the occupant, the driver can be alerted. Therefore, the vehicle can be optimally driven based on the attention information.

以上，参照附图对本发明的优选的实施方式进行了详细说明，但本发明不限于上述例子。只要是具有本发明所属技术领域的普通知识的人就会明确在权利要求书记载的技术的思想的范畴内会想到各种的变更例或修正例，这些当然也属于本发明的技术范围。As mentioned above, although preferred embodiment of this invention was described in detail with reference to drawings, this invention is not limited to the said example. Those with ordinary knowledge in the technical field to which the present invention pertains can clearly think of various changes and modifications within the scope of the technical idea described in the claims, and these also belong to the technical scope of the present invention.

Claims (11)

Translated fromChinese

1.一种车辆用注意提醒装置，其特征在于，具备：1. An attention reminding device for a vehicle, characterized in that it has:语音输入部，其输入车辆的乘员的语音；a voice input section that inputs the voice of an occupant of the vehicle;话语推断部，其基于所述语音推断话语；an utterance inference section that infers utterances based on the speech;注意信息判定部，其判定在所述话语中是否包含与所述车辆的驾驶相关的注意信息；以及An attention information determination section that determines whether or not attention information related to driving of the vehicle is included in the utterance; and通知部，其在所述话语中包含所述注意信息的情况下进行通知。A notification unit that notifies when the attention information is included in the utterance.2.根据权利要求1所述的车辆用注意提醒装置，其特征在于，在所述话语中包含所述注意信息的情况下，所述通知部输出所述话语。2 . The vehicle attention warning device according to claim 1 , wherein the notification unit outputs the utterance when the attention information is included in the utterance. 3 .3.根据权利要求1所述的车辆用注意提醒装置，其特征在于，在所述话语中包含所述注意信息的情况下，所述通知部强调并输出所述话语。3 . The vehicle attention warning device according to claim 1 , wherein when the attention information is included in the utterance, the notification unit emphasizes and outputs the utterance. 4 .4.根据权利要求1～3中任一项所述的车辆用注意提醒装置，其特征在于，所述话语推断部具备将由所述话语推断部推断出的所述话语转换成文字信息的文字转换部，4 . The vehicle attention warning device according to claim 1 , wherein the speech inference unit includes a character conversion for converting the speech estimated by the speech inference unit into character information. 5 . department,所述通知部包含将所述文字信息转换成语音的语音转换部，并将所述语音输出到扬声器。The notification unit includes a voice conversion unit that converts the text information into a voice, and outputs the voice to a speaker.5.根据权利要求4所述的车辆用注意提醒装置，其特征在于，所述通知部包含语音强调部，在所述话语中包含所述注意信息的情况下，所述语音强调部强调经过所述转换的语音的音量。5 . The vehicle attention warning device according to claim 4 , wherein the notification unit includes a voice emphasis unit, and when the attention information is included in the utterance, the voice emphasis unit emphasizes the passage of the the volume of the converted speech.6.根据权利要求1～3中任一项所述的车辆用注意提醒装置，其特征在于，所述话语推断部具备将由所述话语推断部推断出的所述话语转换成文字信息的文字转换部，6 . The vehicle attention warning device according to claim 1 , wherein the speech inference unit includes a character conversion for converting the speech estimated by the speech inference unit into character information. 7 . department,所述通知部将所述文字信息输出到显示装置。The notification unit outputs the character information to a display device.7.根据权利要求4所述的车辆用注意提醒装置，其特征在于，所述通知部包含文字强调部，在所述话语中包含所述注意信息的情况下，所述文字强调部强调所述文字信息。7 . The vehicle attention warning device according to claim 4 , wherein the notification unit includes a character emphasis unit, and when the attention information is included in the utterance, the character emphasis unit emphasizes the text information.8.根据权利要求1～3中任一项所述的车辆用注意提醒装置，其特征在于，所述车辆用注意提醒装置具备确定作为所述注意信息的输出目标的被信息提示者的被信息提示者确定部，8 . The caution reminder device for a vehicle according to claim 1 , wherein the caution reminder device for a vehicle includes an information recipient that specifies a recipient who is an output target of the caution information. 9 . Prompter Determination Department,在所述话语中包含所述注意信息的情况下，所述被信息提示者确定部将所述车辆的驾驶员确定为所述被信息提示者。When the attention information is included in the utterance, the information-presented person specifying unit specifies the driver of the vehicle as the information-presented person.9.根据权利要求8所述的车辆用注意提醒装置，其特征在于，在所述话语中不包含所述注意信息的情况下，所述被信息提示者确定部将所述车辆的乘员全员确定为所述被信息提示者。9 . The caution reminder device for a vehicle according to claim 8 , wherein, when the caution information is not included in the speech, the information-represented person specifying unit assigns all occupants of the vehicle to the vehicle. 10 . Determined to be the informant.10.一种车辆用注意提醒方法，其特征在于，包括：10. A vehicle attention reminder method, characterized in that, comprising:输入车辆的乘员的语音的步骤；the step of entering the speech of an occupant of the vehicle;基于所述语音来推断话语的步骤；the step of inferring utterances based on said speech;判定所述话语中是否包含与所述车辆的驾驶相关的注意信息的步骤；以及the step of determining whether the utterance contains attention information related to driving of the vehicle; and在所述话语中包含所述注意信息的情况下进行通知的步骤。The step of notifying if the attention information is included in the utterance.11.一种记录介质，其特征在于，用于使计算机作为以下装置而发挥作用：11. A recording medium for causing a computer to function as the following means:输入车辆的乘员的语音的装置；means for inputting the speech of the occupants of the vehicle;基于所述语音推断来话语的装置；means for speaking based on said speech inference;判定在所述话语中是否包含与所述车辆的驾驶相关的注意信息的装置；means for determining whether attention information related to driving of the vehicle is included in the utterance;在所述话语中包含所述注意信息的情况下进行通知的装置。Means for notifying if the attention information is included in the utterance.

Images